© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12202
    Prev
    Next
    INDEX
    Explanations

    return to their duty posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Terr
    -0.21
    åŁ¹
    -0.20
     Gee
    -0.19
    åİĨæŶ
    -0.19
    Ascii
    -0.19
    åł¡åŀĴ
    -0.18
     Commentary
    -0.18
     terr
    -0.18
     exem
    -0.18
    gle
    -0.18
    POSITIVE LOGITS
    åħĪè¡Į
    0.27
    ç«ĭåį³
    0.27
     interim
    0.25
     immediate
    0.24
    æ¸IJ
    0.24
    å·²ç»ıå¼Ģå§ĭ
    0.24
     immediately
    0.23
     Immediately
    0.22
    马ä¸Ĭ
    0.22
    æļĤæŶ
    0.21
    Activations Density 0.123%

    No Known Activations